Protein residue contact map is a compact representation of secondary structure of protein. Due to the information hold in the contact map, attentions from researchers in related field were drawn and plenty of works have been done throughout the past decade. Artificial intelligence approaches have been widely adapted in related works such as neural networks, genetic programming, and Hidden Markov model as well as support vector machine. However, the performance of the prediction was not generalized which probably depends on the data used to train and generate the prediction model. This situation shown the importance of the features or information used in affecting the prediction performance. In this research, support vector machine was used to predict protein residue contact map on different combination of features in order to show and analyze the effectiveness of the features. contact map, protein residue contact, support vector machine, protein structure prediction I. INTRODUCTION IOINFORMATICS is defined as a field of science that involve the application of statistics and computer science in the field of biology. It is an emerging field undergoing rapid growth in the past few decades. Bioinformatics at first is applied in the creation and maintenance of database of biological information and currently also applied in tasks like interpretation and analysis of biological data includes deoxyribonucleic acid (DNA) sequences, ribonucleic acid (RNA) sequences, protein structures, protein sequences and protein domains which referred as computational biology. The branch of bioinformatics that consists of the analysis and prediction of three dimensional structures of biological macromolecules such as DNA, RNA and proteins referred as structural bioinformatics. In structural bioinformatics, one of the challenges is the prediction of protein structure. Protein is one of the most important compounds in human body. Function of a protein is defined by its structure. Protein structures are divided into few categories such as primary structure, secondary structure, tertiary structure, and quaternary structure. A protein consists of more than one linear chain of amino acids that further fold into polypeptides Chan Weng Howe is with Artificial Intelligence and Bioinformatics Research Group, Faculty of Computer Science and Information System, Universiti Teknologi Malaysia, 81310 Skudai, Johor, Malaysia. (email: stephenchanwh@gmail.com) Mohd Saberi Mohamad is with Artificial Intelligence and Bioinformatics Research Group, Faculty of Computer Science and Information System, Universiti Teknologi Malaysia, 81310 Skudai, Johor, Malaysia. (email: saberi@utm.my) of different structures and features. Protein structure prediction has played an important role in protein design which is essential is several fields for instance medicine. In protein structure prediction, different information of protein has been used and one of them is protein contact map which is used in this research. Protein contact map is a compact representation of three7dimensional conformations of a protein. A contact map is a two7dimensional Boolean matrix representation of protein structure, each of the dimensions is represented by residue number, while the value is true when the corresponding residues are spatial neighbours and false otherwise [2]. Protein contact map is binary symmetric matrices where non7zero values represent the residue in contact [3] and this is illustrated in an example as in Fig. 1. Fig. 1 Example of contact map of HSP760 protein fragment According to Fig. 1, Secondary structures are highlighted along the both axis. Both α7helices and β7strands represented by black and grey respectively. While on the left side, the structural protein features are shown: (a) Anti7parallel sheet contacts; (b) parallel sheet contacts; (c) contacts between helical regions. Generally, a residue pair considers as a contact when the distance between the residues within a pair is below a defined distance threshold. The distance threshold is calculated in angstrom (Å) which measure as 0.1 nanometers or 1 x 10710 metres. In CASP (Critical Assessment of Techniques for Protein Structure Prediction), default distance Chan Weng Howe and Mohd Saberi Mohamad Protein Residue Contact Prediction using Support Vector Machine B World Academy of Science, Engineering and Technology 60 2011 1985